© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 4843
    Prev
    Next
    INDEX
    Explanations

    key figures and their contributions in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     however
    -0.94
     and
    -0.92
    however
    -0.85
     entanto
    -0.83
     porém
    -0.79
     però
    -0.78
    However
    -0.75
     aber
    -0.75
     însă
    -0.73
    ագրություններ
    -0.72
    POSITIVE LOGITS
     accordingly
    0.76
     thereof
    0.75
     therefrom
    0.70
     therein
    0.68
     correspondingly
    0.66
     consequently
    0.66
     daarvan
    0.65
     therefor
    0.63
     therewith
    0.58
    それを
    0.58
    Activations Density 0.872%

    No Known Activations